Base station power optimization for green networks using reinforcement learning

Download
2019
Aktaş, Semih
The next generation mobile networks have to provide high data rates, extremely low latency, and support high connection density. To meet these requirements, the number of base stations will have to increase and this increase will lead to an energy consumption issue. Therefore ``green'' approaches to the network operation will gain importance. Reducing the energy consumption of base stations is essential for going green and also it helps service providers to reduce operational expenses. However, achieving energy savings without degrading the quality of service is a huge challenge. In order to address this issue, we propose a machine learning based intelligent solution that also incorporates a network simulator. We develop a reinforcement based learning model by using deep deterministic policy gradient algorithm. Our model update frequently the policy of network switches in a way that, packet be forwarded to base stations with an optimized power level. The policies taken by the network controller are evaluated with a network simulator to ensure the energy consumption reduction and quality of service balance. The reinforcement learning model allows us to constantly learn and adapt to the changing situations in the dynamic network environment, hence having a more robust and realistic intelligent network management policy set. Our results demonstrate that energy efficiency can be enhanced by 32% and 67% in dense and sparse scenarios, respectively.

Suggestions

Base Station Power Optimization for Green Networks Using Reinforcement Learning
Aktaş, Semih; Alemdar, Hande (2021-08-31)
The next generation mobile networks have to provide high data rates, extremely low latency, and support high connection density. To meet these requirements, the number of base stations will have to increase and this increase will lead to an energy consumption issue. Therefore “green” approaches to the network operation will gain importance. Reducing the energy consumption of base stations is essential for going green and also it helps service providers to reduce operational expenses. However, achieving ener...
Analysis and design of dual-polarized wideband patch antennas electromagnetically excited with elevated wide strips /
Yılmaz, Adil Fırat; Alatan, Lale; Department of Electrical and Electronics Engineering (2015)
In communication systems like WiMAX, WLAN, 3G, 4G and LTE, design of wideband and dual polarized antennas are required. It is known that bandwidth of patch antennas can be broaden by using thick air substrates. The bandwidth can be further improved by using three dimensional feed strucutures that are electromagnetically coupled to the patch. In this thesis, microstrip patch antennas that are excited by elevated wide strips are studied. First, a linearly polarized antenna is considered and the effects of ant...
Usage of device-to-device communication with multiple antennas at the cell edges Çoklu antenli cihazdan cihaza haberleşme yönteminin hücre kenarindaki alanlarda kullanimi
Erkan, Kerem; Yılmaz, Ali Özgür (2018-07-05)
5G technology is considered to bring dramatic improvements from the large scale data transmission to latency, from reliable data trasmission to energy efficiency. One significant improvement is expected in the communication rates between the mobile users at cell edges. Device-to-device (D2D) communication is an important technique to meet the higher data rates between the mobile users at cell edges compared to standard base station communication. In this paper, important decrease in the outage probability i...
Content Placement Problem in a Hierarchical Collaborative Caching method for 5G networks (CPP-HCC)
Hassanzadeh, Farnaz; Onur, Ertan (2020-01-01)
The increasing demand for video streaming has imposed tremendous data rates and minimal end-to-end latency requirements on 5G mobile networks. Caching content close to the users is one of the conventional ways to meet these requirements. Subsequent requests for the same content can be supplied from the cache with minimal delay. In this paper, we present a content placement problem in a hierarchical collaborative caching (CPP-HCC) in 5G networks that can determine the location of the replica contents by solv...
GreenSlice: An Energy-Efficient Secure Network Slicing Framework
Akin, Ozan; Gulmez, Umut Can; Sazak, Ozan; Yagmur, Osman Ufuk; Angın, Pelin (2022-02-01)
The fifth generation of telecommunication networks comes with various use cases such as Enhanced Mobile Broadband, Ultra-Reliable and Low Latency Communications and Massive Machine Type Communications. These different types of communications have diverse requirements that need to be satisfied while they utilize the same physical infrastructure. By leveraging Software Defined Network (SDN) and Virtual Network Function (VNF) technologies, the 5G network slicing concept can provide end-to-end logical networks ...
Citation Formats
S. Aktaş, “Base station power optimization for green networks using reinforcement learning,” Thesis (M.S.) -- Graduate School of Natural and Applied Sciences. Computer Engineering., Middle East Technical University, 2019.